Ziwei Liu

liuziwei7's activity

• All
• Models
• Datasets
• Spaces
• Buckets
• Papers
• Collections
• Community
• Posts
• Upvotes
• Likes
• Articles

upvoted a paper about 12 hours ago

Video-MME-v2: Towards the Next Stage in Benchmarks for Comprehensive Video Understanding

Paper • 2604.05015 • Published 3 days ago • 188

upvoted a paper 1 day ago

FileGram: Grounding Agent Personalization in File-System Behavioral Traces

Paper • 2604.04901 • Published 3 days ago • 31

upvoted a paper 3 days ago

A Simple Baseline for Streaming Video Understanding

Paper • 2604.02317 • Published 7 days ago • 65

liked a model 4 days ago

weepiess2383/UAE

Image Feature Extraction • Updated 4 days ago • 2

liked a dataset 5 days ago

MMMem-org/HippoCamp

Viewer • Updated 6 days ago • 637 • 3.85k • 5

upvoted 2 papers 6 days ago

HippoCamp: Benchmarking Contextual Agents on Personal Computers

Paper • 2604.01221 • Published 7 days ago • 27

PerceptionComp: A Video Benchmark for Complex Perception-Centric Reasoning

Paper • 2603.26653 • Published 12 days ago • 17

upvoted 2 papers 15 days ago

InfiniteDance: Scalable 3D Dance Generation Towards in-the-wild Generalization

Paper • 2603.13375 • Published 29 days ago • 3

Insight-V++: Towards Advanced Long-Chain Visual Reasoning with Multimodal Large Language Models

Paper • 2603.18118 • Published 21 days ago • 12

liked a model 17 days ago

huuuuuuuuu/InfiniteDance

Updated Jan 22 • 3

liked a Space 18 days ago

Build error

8

Vla4ad

🔥

8

Vision-Language-Action Models for Autonomous Driving: Past

liked 3 datasets 18 days ago

worldbench/occgen

Updated Jun 25, 2025 • 21 • 1

worldbench/lidargen

Updated Jun 25, 2025 • 17 • 1

worldbench/videogen

Updated Dec 22, 2025 • 1.72k • 7

upvoted 2 papers 19 days ago

MonoArt: Progressive Structural Reasoning for Monocular Articulated 3D Reconstruction

Paper • 2603.19231 • Published 20 days ago • 36

Bridging Semantic and Kinematic Conditions with Diffusion-based Discrete Motion Tokenizer

Paper • 2603.19227 • Published 20 days ago • 42

authored a paper 21 days ago

Kinema4D: Kinematic 4D World Modeling for Spatiotemporal Embodied Simulation

Paper • 2603.16669 • Published 22 days ago • 70

upvoted 2 papers 21 days ago

Kinema4D: Kinematic 4D World Modeling for Spatiotemporal Embodied Simulation

Paper • 2603.16669 • Published 22 days ago • 70

Demystifing Video Reasoning

Paper • 2603.16870 • Published 22 days ago • 367

authored a paper 22 days ago

HSImul3R: Physics-in-the-Loop Reconstruction of Simulation-Ready Human-Scene Interactions

Paper • 2603.15612 • Published 23 days ago • 152